Cover Image

Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chanin, David, Dulka, Tomáš, Garriga-Alonso, Adrià
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
by: Chanin, David, et al.
Published: (2025)

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data
by: Chanin, David, et al.
Published: (2026)

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
by: Chanin, David, et al.
Published: (2024)

Are Sparse Autoencoder Benchmarks Reliable?
by: Chanin, David
Published: (2026)

Sparse Autoencoder Features for Classifications and Transferability
by: Gallifant, Jack, et al.
Published: (2025)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
by: Chalnev, Sviatoslav, et al.
Published: (2024)

Biases in the Blind Spot: Detecting What LLMs Fail to Mention
by: Arcuschin, Iván, et al.
Published: (2026)

AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
by: Zhu, Xudong, et al.
Published: (2025)

Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
by: Lan, Michael, et al.
Published: (2024)

Time-Aware Feature Selection: Adaptive Temporal Masking for Stable Sparse Autoencoder Training
by: Li, T. Ed, et al.
Published: (2025)

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
by: Cho, Seonglae, et al.
Published: (2025)

Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation Models
by: Mishra, Anurag
Published: (2026)

Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction
by: Sainsbury, Chris, et al.
Published: (2026)

CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
by: Cho, Seonglae, et al.
Published: (2025)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
by: Marks, Samuel, et al.
Published: (2024)

Among Us: A Sandbox for Measuring and Detecting Agentic Deception
by: Golechha, Satvik, et al.
Published: (2025)

Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
by: Muchane, Mark, et al.
Published: (2025)

ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
by: Butler, Landon, et al.
Published: (2025)

Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
by: Farnik, Lucy, et al.
Published: (2025)

Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
by: Li, Aaron J., et al.
Published: (2025)

Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
by: Bhalla, Usha, et al.
Published: (2025)

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
by: Yu, Zhuohao, et al.
Published: (2025)

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
by: Minegishi, Gouki, et al.
Published: (2025)

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering
by: Wong, Sing Hieng, et al.
Published: (2026)

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
by: Shu, Dong, et al.
Published: (2025)

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines
by: Jørgensen, Mikkel Godsk, et al.
Published: (2026)

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
by: Luo, Sijia, et al.
Published: (2026)

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
by: Shu, Dong, et al.
Published: (2025)

Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder
by: Yang, Xianjun, et al.
Published: (2025)

Sparse Shift Autoencoders for Identifying Concepts from Large Language Model Activations
by: Joshi, Shruti, et al.
Published: (2025)

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
by: Lieberum, Tom, et al.
Published: (2024)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
by: Wang, Xu, et al.
Published: (2026)

Towards Understanding the Robustness of Sparse Autoencoders
by: Saiyed, Ahson, et al.
Published: (2026)

Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders
by: Wang, Xu, et al.
Published: (2025)

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
by: He, Zirui, et al.
Published: (2025)

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models
by: Muhamed, Aashiq, et al.
Published: (2024)

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
by: Jing, Yi, et al.
Published: (2026)

Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
by: Cho, Seonglae, et al.
Published: (2026)

Use Sparse Autoencoders to Discover Unknown Concepts, Not to Act on Known Concepts
by: Peng, Kenny, et al.
Published: (2025)

The Geometry of Concepts: Sparse Autoencoder Feature Structure
by: Li, Yuxiao, et al.
Published: (2024)